to-questionnaire

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill operates as a purely instructional template for generating documentation. It does not request external network access, execute arbitrary code, or access sensitive system credentials. The logic is self-contained within the provided markdown instructions.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface where it ingests user input and writes it to a local filesystem document (to-questionnaire-<slug>.md). 1. Ingestion points: User interaction steps 1 and 2 in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: File-writing in SKILL.md. 4. Sanitization: Absent. The risk is considered minimal as the output is intended for human consumption rather than automated processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 06:39 PM